Gaurav Parmar

I am a PhD student at Carnegie Mellon University. I got my undergraduate degree in Computer Science (with highest honors) from University of California, San Diego in 2020.

My research interests include Computer Vision, Machine Learning and Robotics. I am advised by Jun-Yan Zhu. Prior to this, I have worked with Zhuowen Tu and Jack Silberman at UCSD.

I spent a wonderful summers of 2021 and 2022 interning at Adobe Research working with Krishna Kumar Singh, Yijun Li, Cynthia Lu, and Richard Zhang.

Email  /  Google Scholar  /  LinkedIn

profile photo
Publications

clean-usnob Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing
Gaurav Parmar, Yijun Li , Jingwan (Cynthia) Lu , Richard Zhang , Jun-Yan Zhu , Krishna Kumar Singh
To appear in CVPR, 2022
[Webpage] | [Paper] | [GitHub]
clean-usnob On Aliased Resizing and Surprising Subtleties in GAN Evaluation
Gaurav Parmar, Richard Zhang , Jun-Yan Zhu
To appear in CVPR, 2022
[Webpage] | [Paper] | [GitHub]
clean-usnob Dual Contradistinctive Generative Autoencoder
Gaurav Parmar, Dacheng Li , Kwonjoon Lee, Zhuowen Tu
CVPR, 2021
[Webpage] | [Paper] | [GitHub]
clean-usnob Guided Variational Autoencoder for Disentanglement Learning
Zheng Ding*, Yifan Xu*, Weijian Xu, Gaurav Parmar, Yang Yang, Max Welling, Zhuowen Tu
CVPR, 2020
clean-usnob Geometry-Aware End-to-End Skeleton Detection
Weijian Xu, Gaurav Parmar, Zhuowen Tu
British Machine Vision Conference, 2019
clean-usnob clean-usnob Autonomous Smart Wheelchair: A Social Solution for Individual Need
Isabella Gomez, Gaurav Parmar, Samarth Aggarwal, Nathaniel Mansur, Alexander Guthrie
CHI Conference on Human Factors in Computing Systems EA, 2019
Miscellaneous.
RC car

Modified RC car trained with behavior cloning.

[GitHub]

Simulated RC Car

RL agent trained with Soft Actor Critic to drive autonomously in a simulator.

Trained on two simulators:

Simulator A: The input is 2D lidar scan

Simulator B: The input is a camera frame

SEDS: Project Colossus

Static fire rocket engine test stand

[Project Page]


Website template inspired from [here] and [here]